Chapter 3 - Road Perception in Driver Intention Inference System

Abstract

Road perception and lane detection is a fundamental function of many current advanced driver assistance systems. It is necessary to understand the road structure and traffic context to recognize driver intention, as road structure determines the driving rules and knowledge. Among the road perception systems, lane detection system plays a critical role in the driver intention inference, as the ego-lanes determine how the lane change can be initiated. A large volume of existing studies focus on the study of vision-based lane detection methods because of the extensive knowledge background and the low cost of camera devices. In this section, existing vision-based lane detection studies are reviewed from three main aspects, which are lane detection algorithms, integration methods, and evaluation methods. Next, considering the inevitable limitations that exist in the camera-based lane detection system, the system integration methodologies for constructing more robust detection systems are reviewed and analyzed. The integration methods are further divided into three levels, namely, algorithm, system, and sensor levels. Algorithm level combines different lane detection algorithms, while system level integrates other object detection systems to comprehensively detect lane positions. Sensor level integration uses multimodal sensors to build a robust lane recognition system. Owing to the complexity of evaluating the detection system, and the lack of a common evaluation procedure and uniform metrics in past studies, existing evaluation methods and metrics are analyzed and classified to propose a better evaluation of the lane detection system. Next, a comparison of representative studies is performed. Finally, a discussion on the limitations of current lane detection systems and the future developing trends toward an artificial society, computational experiment, and parallel execution (ACP)-based lane detection framework is proposed.